Explaining Machine Learning to a Non-technical Audience

Описание: An important part of a data scientist’s job is to explain machine learning model predictions. Often, the person receiving the explanation will be non-technical. If you start talking about cost functions, hyperparameters or p-values you will be met with blank stares. We need to translate these technical concepts into layman’s terms. This process can be more challenging than building the model itself.

So, we will explore how you can give human-friendly explanations. We will do this by discussing some key characteristics of a good explanation. These include whether the reasons are true, given at an appropriate level and the number of reasons provided. When it comes to the individual reasons given we must consider if they are significant, general, abnormal or contrasting. Along the way, we will use SHAP plots to ground the characteristics with an actual Explainable AI method. This will show us how these methods can be used as a basis for human-friendly explanations.

🚀 Free Course 🚀
Signup here: https://mailchi.mp/40909011987b/signup
XAI course: https://adataodyssey.com/courses/xai-...
SHAP course: https://adataodyssey.com/courses/shap...

🚀 Companion article with link to code (no-paywall link): 🚀
https://medium.com/data-science/the-a...

🚀 Useful playlists 🚀
XAI:    • Explainable AI (XAI)  
SHAP:    • SHAP  
Algorithm fairness:    • Algorithm Fairness  

🚀 Get in touch 🚀
Medium:   / conorosullyds  
Threads: https://www.threads.net/@conorosullyds
Twitter:   / conorosullyds  
Website: https://adataodyssey.com/

🚀 Chapters 🚀
00:00 Introduction
01:45 Tip1: Local vs global explanations
03:46 Characteristics of a good explanation
07:12 Significant reasons
09:02 General reasons
10:02 Abnormal reasons
11:13 Contrasting reasons